def test_uniform_vector(self):
random = RandomStreams(utt.fetch_seed())
low = tensor.dvector()
high = tensor.dvector()
out = random.uniform(low=low, high=high)
assert out.ndim == 1
f = function([low, high], out)
low_val = [0.1, 0.2, 0.3]
high_val = [1.1, 2.2, 3.3]
seed_gen = np.random.RandomState(utt.fetch_seed())
numpy_rng = np.random.RandomState(int(seed_gen.randint(2**30)))
# Arguments of size (3,)
val0 = f(low_val, high_val)
numpy_val0 = numpy_rng.uniform(low=low_val, high=high_val)
assert np.all(val0 == numpy_val0)
# arguments of size (2,)
val1 = f(low_val[:-1], high_val[:-1])
numpy_val1 = numpy_rng.uniform(low=low_val[:-1], high=high_val[:-1])
assert np.all(val1 == numpy_val1)
# Specifying the size explicitly
g = function([low, high], random.uniform(low=low,
high=high,
size=(3, )))
val2 = g(low_val, high_val)
numpy_rng = np.random.RandomState(int(seed_gen.randint(2**30)))
numpy_val2 = numpy_rng.uniform(low=low_val, high=high_val, size=(3, ))
assert np.all(val2 == numpy_val2)
with pytest.raises(ValueError):
g(low_val[:-1], high_val[:-1])
def test_default_dtype(self):
random = RandomStreams(utt.fetch_seed())
low = tensor.dscalar()
high = tensor.dscalar()
# Should not silently downcast from low and high
out0 = random.uniform(low=low, high=high, size=(42, ))
assert out0.dtype == "float64"
f0 = function([low, high], out0)
val0 = f0(-2.1, 3.1)
assert val0.dtype == "float64"
# Should downcast, since asked explicitly
out1 = random.uniform(low=low, high=high, size=(42, ), dtype="float32")
assert out1.dtype == "float32"
f1 = function([low, high], out1)
val1 = f1(-1.1, 1.1)
assert val1.dtype == "float32"
# Should use floatX
lowf = tensor.fscalar()
highf = tensor.fscalar()
outf = random.uniform(low=lowf, high=highf, size=(42, ))
assert outf.dtype == config.floatX
ff = function([lowf, highf], outf)
valf = ff(np.float32(-0.1), np.float32(0.3))
assert valf.dtype == config.floatX
def test_vector_arguments(self):
random = RandomStreams(utt.fetch_seed())
low = tensor.dvector()
out = random.uniform(low=low, high=1)
assert out.ndim == 1
f = function([low], out)
seed_gen = np.random.RandomState(utt.fetch_seed())
numpy_rng = np.random.RandomState(int(seed_gen.randint(2**30)))
val0 = f([-5, 0.5, 0, 1])
val1 = f([0.9])
numpy_val0 = numpy_rng.uniform(low=[-5, 0.5, 0, 1], high=1)
numpy_val1 = numpy_rng.uniform(low=[0.9], high=1)
assert np.all(val0 == numpy_val0)
assert np.all(val1 == numpy_val1)
high = tensor.vector()
outb = random.uniform(low=low, high=high)
assert outb.ndim == 1
fb = function([low, high], outb)
numpy_rng = np.random.RandomState(int(seed_gen.randint(2**30)))
val0b = fb([-4.0, -2], [-1, 0])
val1b = fb([-4.0], [-1])
numpy_val0b = numpy_rng.uniform(low=[-4.0, -2], high=[-1, 0])
numpy_val1b = numpy_rng.uniform(low=[-4.0], high=[-1])
assert np.all(val0b == numpy_val0b)
assert np.all(val1b == numpy_val1b)
with pytest.raises(ValueError):
fb([-4.0, -2], [-1, 0, 1])
# TODO: do we want that?
# with pytest.raises(ValueError):
# fb([-4., -2], [-1])
size = tensor.lvector()
outc = random.uniform(low=low, high=high, size=size, ndim=1)
fc = function([low, high, size], outc)
numpy_rng = np.random.RandomState(int(seed_gen.randint(2**30)))
val0c = fc([-4.0, -2], [-1, 0], [2])
val1c = fc([-4.0], [-1], [1])
numpy_val0c = numpy_rng.uniform(low=[-4.0, -2], high=[-1, 0])
numpy_val1c = numpy_rng.uniform(low=[-4.0], high=[-1])
assert np.all(val0c == numpy_val0c)
assert np.all(val1c == numpy_val1c)
with pytest.raises(ValueError):
fc([-4.0, -2], [-1, 0], [1, 2])
with pytest.raises(ValueError):
fc([-4.0, -2], [-1, 0], [2, 1])
with pytest.raises(ValueError):
fc([-4.0, -2], [-1, 0], [1])
with pytest.raises(ValueError):
fc([-4.0, -2], [-1], [1])
def test_mixed_shape(self):
# Test when the provided shape is a tuple of ints and scalar vars
random = RandomStreams(utt.fetch_seed())
shape0 = tensor.lscalar()
shape = (shape0, 3)
f = function([shape0], random.uniform(size=shape, ndim=2))
assert f(2).shape == (2, 3)
assert f(8).shape == (8, 3)
g = function([shape0], random.uniform(size=shape))
assert g(2).shape == (2, 3)
assert g(8).shape == (8, 3)
def test_mixed_shape_bcastable(self):
# Test when the provided shape is a tuple of ints and scalar vars
random = RandomStreams(utt.fetch_seed())
shape0 = tensor.lscalar()
shape = (shape0, 1)
u = random.uniform(size=shape, ndim=2)
assert u.broadcastable == (False, True)
f = function([shape0], u)
assert f(2).shape == (2, 1)
assert f(8).shape == (8, 1)
v = random.uniform(size=shape)
assert v.broadcastable == (False, True)
g = function([shape0], v)
assert g(2).shape == (2, 1)
assert g(8).shape == (8, 1)
def test_default_updates(self):
# Basic case: default_updates
random_a = RandomStreams(utt.fetch_seed())
out_a = random_a.uniform((2, 2))
fn_a = function([], out_a)
fn_a_val0 = fn_a()
fn_a_val1 = fn_a()
assert not np.all(fn_a_val0 == fn_a_val1)
nearly_zeros = function([], out_a + out_a - 2 * out_a)
assert np.all(abs(nearly_zeros()) < 1e-5)
# Explicit updates #1
random_b = RandomStreams(utt.fetch_seed())
out_b = random_b.uniform((2, 2))
fn_b = function([], out_b, updates=random_b.updates())
fn_b_val0 = fn_b()
fn_b_val1 = fn_b()
assert np.all(fn_b_val0 == fn_a_val0)
assert np.all(fn_b_val1 == fn_a_val1)
# Explicit updates #2
random_c = RandomStreams(utt.fetch_seed())
out_c = random_c.uniform((2, 2))
fn_c = function([], out_c, updates=[out_c.update])
fn_c_val0 = fn_c()
fn_c_val1 = fn_c()
assert np.all(fn_c_val0 == fn_a_val0)
assert np.all(fn_c_val1 == fn_a_val1)
# No updates at all
random_d = RandomStreams(utt.fetch_seed())
out_d = random_d.uniform((2, 2))
fn_d = function([], out_d, no_default_updates=True)
fn_d_val0 = fn_d()
fn_d_val1 = fn_d()
assert np.all(fn_d_val0 == fn_a_val0)
assert np.all(fn_d_val1 == fn_d_val0)
# No updates for out
random_e = RandomStreams(utt.fetch_seed())
out_e = random_e.uniform((2, 2))
fn_e = function([], out_e, no_default_updates=[out_e.rng])
fn_e_val0 = fn_e()
fn_e_val1 = fn_e()
assert np.all(fn_e_val0 == fn_a_val0)
assert np.all(fn_e_val1 == fn_e_val0)
def test_symbolic_shape(self):
random = RandomStreams(utt.fetch_seed())
shape = tensor.lvector()
f = function([shape], random.uniform(size=shape, ndim=2))
assert f([2, 3]).shape == (2, 3)
assert f([4, 8]).shape == (4, 8)
with pytest.raises(ValueError):
f([4])
with pytest.raises(ValueError):
f([4, 3, 4, 5])
def test_ndim(self):
# Test that the behaviour of 'ndim' optional parameter
# 'ndim' is an optional integer parameter, specifying the length
# of the 'shape', passed as a keyword argument.
# ndim not specified, OK
random = RandomStreams(utt.fetch_seed())
fn = function([], random.uniform((2, 2)))
# ndim specified, consistent with shape, OK
random2 = RandomStreams(utt.fetch_seed())
fn2 = function([], random2.uniform((2, 2), ndim=2))
val1 = fn()
val2 = fn2()
assert np.all(val1 == val2)
# ndim specified, inconsistent with shape, should raise ValueError
random3 = RandomStreams(utt.fetch_seed())
with pytest.raises(ValueError):
random3.uniform((2, 2), ndim=1)
def test_tutorial(self):
srng = RandomStreams(seed=234)
rv_u = srng.uniform((2, 2))
rv_n = srng.normal((2, 2))
f = function([], rv_u)
g = function([], rv_n,
no_default_updates=True) # Not updating rv_n.rng
nearly_zeros = function([], rv_u + rv_u - 2 * rv_u)
assert np.all(f() != f())
assert np.all(g() == g())
assert np.all(abs(nearly_zeros()) < 1e-5)
assert isinstance(rv_u.rng.get_value(borrow=True),
np.random.RandomState)
def test_uniform(self):
# Test that RandomStreams.uniform generates the same results as numpy
# Check over two calls to see if the random state is correctly updated.
random = RandomStreams(utt.fetch_seed())
fn = function([], random.uniform((2, 2), -1, 1))
fn_val0 = fn()
fn_val1 = fn()
rng_seed = np.random.RandomState(utt.fetch_seed()).randint(2**30)
rng = np.random.RandomState(int(rng_seed)) # int() is for 32bit
numpy_val0 = rng.uniform(-1, 1, size=(2, 2))
numpy_val1 = rng.uniform(-1, 1, size=(2, 2))
assert np.allclose(fn_val0, numpy_val0)
assert np.allclose(fn_val1, numpy_val1)
def test_setitem(self):
random = RandomStreams(234)
out = random.uniform((2, 2))
fn = function([], out, updates=random.updates())
random.seed(888)
rng = np.random.RandomState(utt.fetch_seed())
random[out.rng] = np.random.RandomState(utt.fetch_seed())
fn_val0 = fn()
fn_val1 = fn()
numpy_val0 = rng.uniform(size=(2, 2))
numpy_val1 = rng.uniform(size=(2, 2))
assert np.allclose(fn_val0, numpy_val0)
assert np.allclose(fn_val1, numpy_val1)
def test_seed_fn(self):
random = RandomStreams(234)
fn = function([], random.uniform((2, 2)), updates=random.updates())
random.seed(utt.fetch_seed())
fn_val0 = fn()
fn_val1 = fn()
rng_seed = np.random.RandomState(utt.fetch_seed()).randint(2**30)
rng = np.random.RandomState(int(rng_seed)) # int() is for 32bit
numpy_val0 = rng.uniform(size=(2, 2))
numpy_val1 = rng.uniform(size=(2, 2))
assert np.allclose(fn_val0, numpy_val0)
assert np.allclose(fn_val1, numpy_val1)
def test_broadcast_arguments(self):
random = RandomStreams(utt.fetch_seed())
low = tensor.dvector()
high = tensor.dcol()
out = random.uniform(low=low, high=high)
assert out.ndim == 2
f = function([low, high], out)
rng_seed = np.random.RandomState(utt.fetch_seed()).randint(2**30)
numpy_rng = np.random.RandomState(int(rng_seed))
val0 = f([-5, 0.5, 0, 1], [[1.0]])
val1 = f([0.9], [[1.0], [1.1], [1.5]])
val2 = f([-5, 0.5, 0, 1], [[1.0], [1.1], [1.5]])
numpy_val0 = numpy_rng.uniform(low=[-5, 0.5, 0, 1], high=[1.0])
numpy_val1 = numpy_rng.uniform(low=[0.9], high=[[1.0], [1.1], [1.5]])
numpy_val2 = numpy_rng.uniform(low=[-5, 0.5, 0, 1],
high=[[1.0], [1.1], [1.5]])
assert np.all(val0 == numpy_val0)
assert np.all(val1 == numpy_val1)
assert np.all(val2 == numpy_val2)
def test_connection_pattern(self, cls_ofg):
# Basic case
x, y, z = tt.matrices("xyz")
out1 = x * y
out2 = y * z
op1 = cls_ofg([x, y, z], [out1, out2])
results = op1.connection_pattern(None)
expect_result = [[True, False], [True, True], [False, True]]
assert results == expect_result
# Graph with ops that don't have a 'full' connection pattern
# and with ops that have multiple outputs
m, n, p, q = tt.matrices("mnpq")
o1, o2 = op1(m, n, p)
out1, out2 = op1(o1, q, o2)
op2 = cls_ofg([m, n, p, q], [out1, out2])
results = op2.connection_pattern(None)
expect_result = [[True, False], [True, True], [False, True],
[True, True]]
assert results == expect_result
# Inner graph where some computation doesn't rely on explicit inputs
srng = RandomStreams(seed=234)
rv_u = srng.uniform((2, 2))
x, y = tt.matrices("xy")
out1 = x + rv_u
out2 = y + 3
out3 = 3 + rv_u
op3 = cls_ofg([x, y], [out1, out2, out3])
results = op3.connection_pattern(None)
expect_result = [
[True, False, False],
[False, True, False],
[True, False, True],
]
assert results == expect_result
def test_default_shape(self):
random = RandomStreams(utt.fetch_seed())
f = function([], random.uniform())
g = function([], random.multinomial())
# seed_rng is generator for generating *seeds* for RandomStates
seed_rng = np.random.RandomState(utt.fetch_seed())
uniform_rng = np.random.RandomState(int(seed_rng.randint(2**30)))
multinomial_rng = np.random.RandomState(int(seed_rng.randint(2**30)))
val0 = f()
val1 = f()
numpy_val0 = uniform_rng.uniform()
numpy_val1 = uniform_rng.uniform()
assert np.allclose(val0, numpy_val0)
assert np.allclose(val1, numpy_val1)
for i in range(
10
): # every test has 50% chance of passing even with non-matching random states
val2 = g()
numpy_val2 = multinomial_rng.multinomial(n=1, pvals=[0.5, 0.5])
assert np.all(val2 == numpy_val2)
class Graph:
def __init__(self, seed=123):
self.rng = RandomStreams(seed)
self.y = self.rng.uniform(size=(1, ))